An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

An AI-powered chatbot that answers student questions using university PDFs with the help of Google's Gemini API and RAG (Retrieval-Augmented Generation) architecture.

Built for HackRx 6.0 – Bajaj Finserv’s Annual Hackathon, this backend system enables intelligent query–retrieval over large documents using LLMs, semantic search, and explainable decision logic.

Streamlit-based chatbot to interact with PDFs using Retrieval-Augmented Generation (RAG), FAISS, Sentence Transformers, and Mistral LLM

Genr-Kit: The ultimate open-source playground for multi-modal AI. One toolkit to build it all: from text and image generation to speech synthesis and analysis, powered by Gradio and Transformers.

PolicyBot AI Agent is an enterprise-grade intelligent document question-answering system built as an AI agent that can interpret and answer questions about company policies using Retrieval-Augmented Generation (RAG) techniques and general queries.

🚀 Prototype and deploy generative AI applications with ease using Python, Gradio, and Transformers for text, image, and speech tasks.

AI-Powered Document Q&A System for Confluence

Chat With My PDFs is a web-based AI application that allows users to upload PDF documents and ask questions about their content using AI-powered document understanding.

AI-Powered Research Assistant using RAG is a Streamlit web application that uses Retrieval-Augmented Generation (RAG) with Large Language Models to analyze documents and answer user queries with context-aware responses. It performs semantic search over embedded document chunks and generates accurate answers based on retrieved information.

End-to-end RAG pipeline with semantic search, FAISS vector database, Groq LLM integration, and Streamlit UI for document question answering.

A Streamlit-based multi-PDF document Q&A system using Retrieval-Augmented Generation (RAG) with Llama-3 via Groq and ChromaDB.

AskMyDocs helps you chat with your PDFs: upload, ask, and get cited, factual answers. Built with Streamlit and LangChain, featuring swap-in components for chunking, embeddings, and vector stores.

A Streamlit-based app for asking questions directly from uploaded documents using Gemini embeddings and a language model. Supports PDF, TXT, and DOCX files. Fast, simple, and powerful document-based QA.

Notebook-based Retrieval-Augmented Generation (RAG) system for question answering over custom documents.

Document Question Answering using Retrieval-Augmented Generation

AI-powered Resume Chatbot using Retrieval-Augmented Generation (RAG), FAISS, and open-source LLMs to answer resume-based queries.

Retrieval-Augmented Document QA system using LangChain, FAISS, and FastAPI to answer questions grounded in custom documents with source citations. Dockerized and deployed on AWS EC2.

RAG PDF Q&A API (FastAPI + Chroma + SentenceTransformers + Docker)

Local RAG-based document intelligence assistant using Mistral, FAISS, and Streamlit.

A lightweight, modular Retrieval-Augmented Generation (RAG) system built with Streamlit, FAISS, and LLMs like OpenAI and Ollama. Upload documents, embed them, and ask intelligent questions with real-time context-aware responses.

LangChain-based RAG pipeline with chunking, embeddings, vector indexing, retrieval, and LLM response generation.

Turn your documents into instant answers with FAISS + Streamlit.

📝 Generate AI-driven quiz questions effortlessly, enhancing educators' content creation with diverse formats and customizable difficulty levels.

📄 Create a local, free Retrieval-Augmented Q&A system to easily extract answers from your personal documents in minutes.